EP2709060B1 - Procédé et appareil permettant de déterminer un point de regard fixe sur un objet tridimensionnel - Google Patents

Procédé et appareil permettant de déterminer un point de regard fixe sur un objet tridimensionnel Download PDF

Info

Publication number
EP2709060B1
EP2709060B1 EP12184725.5A EP12184725A EP2709060B1 EP 2709060 B1 EP2709060 B1 EP 2709060B1 EP 12184725 A EP12184725 A EP 12184725A EP 2709060 B1 EP2709060 B1 EP 2709060B1
Authority
EP
European Patent Office
Prior art keywords
scene
gaze
objects
endpoint
image
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
EP12184725.5A
Other languages
German (de)
English (en)
Other versions
EP2709060A1 (fr
Inventor
Jan Hoffmann
Tom Sengelaub
Denis Williams
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Apple Inc
Original Assignee
Apple Inc
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Apple Inc filed Critical Apple Inc
Priority to EP12184725.5A priority Critical patent/EP2709060B1/fr
Priority to IN1984DEN2015 priority patent/IN2015DN01984A/en
Priority to CN201380048140.XA priority patent/CN104685541B/zh
Priority to JP2015531598A priority patent/JP6808320B2/ja
Priority to PCT/EP2013/069236 priority patent/WO2014041188A1/fr
Priority to US14/428,608 priority patent/US10223808B2/en
Publication of EP2709060A1 publication Critical patent/EP2709060A1/fr
Priority to US16/290,934 priority patent/US10699439B2/en
Priority to JP2019071195A priority patent/JP6690041B2/ja
Application granted granted Critical
Publication of EP2709060B1 publication Critical patent/EP2709060B1/fr
Priority to US16/878,932 priority patent/US11676302B2/en
Priority to US18/111,099 priority patent/US11948332B2/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
    • G06T7/75—Determining position or orientation of objects or cameras using feature-based methods involving models
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B3/00—Apparatus for testing the eyes; Instruments for examining the eyes
    • A61B3/10—Objective types, i.e. instruments for examining the eyes independent of the patients' perceptions or reactions
    • A61B3/113—Objective types, i.e. instruments for examining the eyes independent of the patients' perceptions or reactions for determining or recording eye movement
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/60—Type of objects
    • G06V20/64—Three-dimensional objects
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/18—Eye characteristics, e.g. of the iris
    • G06V40/19—Sensors therefor
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/18—Eye characteristics, e.g. of the iris
    • G06V40/193—Preprocessing; Feature extraction
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2200/00—Indexing scheme for image data processing or generation, in general
    • G06T2200/04—Indexing scheme for image data processing or generation, in general involving 3D image data
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10028—Range image; Depth image; 3D point clouds
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20076—Probabilistic image processing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30196—Human being; Person
    • G06T2207/30201—Face

Definitions

  • the present invention relates to a method and an apparatus for gaze endpoint determination, in particular for determining a gaze endpoint of a subject on a three-dimensional object in space.
  • the gaze direction of the person (or a representation thereof like a pupil/CR combination, cornea center and pupil/limbus etc.) is to be found.
  • Eye Trackers observe features of the eye like the pupil, the limbus, blood vessels on the sclera, the eyeball or reflections of light sources (corneal reflections) in order to calculate the direction of the gaze.
  • This gaze direction is then mapped to an image of the scene captured by a head-mounted scene camera or a scene camera at any fixed location.
  • the head-mounted scene camera is fixed with respect to the head, and therefore such a mapping can be performed, once a corresponding calibration has been executed.
  • a user may have to gaze at several defined points in the scene image captured by the head-mounted camera.
  • the calibration can be performed resulting in a transformation which maps a gaze direction to a corresponding point in the scene image.
  • any kind of eye tracker can be used if it allows mapping the gaze direction into images of a head-mounted scene camera.
  • This approach enables the determination of a gaze point in the scene image as taken by the head-mounted scene camera.
  • the gaze point in the scene image as captured by the head-mounted scene camera can change due to the movement of the subject, to a point in a (stable) reference image which does not move and which corresponds to a "real world" object or an image thereof.
  • the reference image thereby typically is taken from a different camera position than the scene image taken by the head-mounted scene camera, because the scene camera may move together with the head of the user.
  • WO 2010/083853 A1 discloses to use active IR markers for that purpose, which are fixed at certain locations, e.g. attached to a bookshelf. The locations of these markers are first detected with respect to a "test scene" which acts as a "reference" image obtained by the head-mounted camera, by use of two orthogonal IR line detectors which detect the two orthogonal angles by detecting the maximum intensity of the two line sensors. The detected angles of an IR source correspond to its location in the reference image.
  • the angles of the markers are detected for a later detected scene taken by the head-mounted camera from a different position, thereby detecting the location of the IR sources in the later scene image.
  • the "perspective projection” which is the mapping that transforms the locations of the IR sources as detected in an image taken later (a scene image), when the head-mounted camera is at a different location, to the locations of the IR light sources in the test image (or reference image). With this transformation a gaze point as determined later for the scene image can also be transformed into the corresponding (actual) gaze point in the test image.
  • the mapping of the gaze point from the actual "scene image” to a stable reference image which is time invariant becomes possible by defining the plane on which the gaze point is mapped in relation to scene stable markers instead of to the eye tracker (ET).
  • ET eye tracker
  • IR sources as artificial markers the locations of which can be detected by orthogonal IR line detectors to detect the angles of maximum emission.
  • a system comprising: an eye tracking unit adapted to determine the gaze directions (L 1 , L 2 ) of two eyes of a subject; a subject tracking unit adapted to determine a position comprising location and orientation of the head of the subject and /or the eye tracking unit in a reference coordinate system; a 3D scene structure representation unit that represents a plurality of objects of a real- world scene through their 3D position and/or structure through coordinates in the reference coordinate system to thereby provide a 3D structure representation of the scene; a calculating unit for: determining a gaze endpoint (G) in the reference coordinate system based on the intersection of the gaze directions of the two eyes of the subject and the position; determining a plurality of respective distances (D 1 , D 2 ) between the gaze endpoint and the plurality of objects; and determining which object of the plurality of objects the subject is gazing at based on the respective distances between the gaze endpoint and the plurality of objects.
  • G gaze endpoint
  • D 1 , D 2 respective distances
  • an eye tracker and a head tracker there can be determined not only a gaze point on a 2D plane but also an object the subject is gazing at and/or the gaze endpoint in 3D.
  • the system comprises a module for calculating the gaze endpoint based on the intersection of the gaze directions of the two eyes of the subject, and/or a module for determining the object the subject is gazing at based on the calculated gaze endpoint and the 3D position and/or 3D structure of the objects of the real world scene.
  • the gaze endpoint By using the vergence to calculate the intersection of the gaze direction of the eyes of the subject there can be determined the gaze endpoint. This gaze endpoint can then be used to determine the object the user is gazing at.
  • the object being gazed at is determined as the object the subject is gazing at by choosing the object whose 3D position and/or structure is closest to the calculated gaze endpoint.
  • said eye tracking unit which is adapted to determining the gaze direction of the said one or more eyes of said subject is adapted to determine a probability distribution of said gaze direction of said one or more eyes, and wherein said calculating unit for determining the object being gazed at determines for one or more objects the probability of said objects being gazed at based on a probability distribution of gaze endpoints.
  • the position of the scene camera is known or determined by some position determination or object tracking mechanism and the mapping is performed by performing a projection of the 3D gaze endpoint onto an image of said scene camera.
  • an arbitrary scene image can be generated not by taking an image using a scene camera but instead by generating it based on the 3D structure representation.
  • the gaze endpoint or the object being gazed at can be indicated or visualized by projecting the gaze endpoint onto the scene image or by e.g. highlighting the object which has been determined as the object of the 3D structure being gazed at in the scene image.
  • said eye tracker is a head-mounted eye tracker; and/or said scene camera is a head-mounted scene camera.
  • Head-mounted eye tracker and head-mounted scene cameras are convenient implementations of these devices. Moreover, if the eye tracker is head-mounted, then the head tracker automatically also delivers the position/orientation of the eye tracker. The same is true for the scene camera. Using the position (location and orientation) of the head as determined by the head tracker one can determine based on the gaze direction as determined by the head-mounted eye tracker in the coordinate system of the eye tracker a corresponding gaze direction in the reference coordinate system of the head tracker. This can be done by a simple transformation which transforms the gaze direction from the eye tracker's coordinate system into the coordinate system of the head tracker using the head location and orientation as determined by the head tracker. The position delivered by the head tracker automatically also delivers the position of the eye tracker through the given setup in which the eye tracker is fixed to the head and has a defined spatial relationship with the head, e.g. by the mounting frame through which it is mounted on the head.
  • said 3D Structure representation unit comprises a 3D scene structure detection unit that is adapted to determine the 3D structure and position of objects of the scene or their geometric surface structure in the reference coordinate system to obtain a 3D structure representation of the real-world scene.
  • the 3D structure or at least the relevant, visible part of it can be directly obtained from the scene by using the structure detection unit.
  • said 3D structure detection unit comprises one of the following:
  • the recording of gaze endpoints and the mapping to one or more possibly different scene images can be performed over time, possibly even for different subjects, thereby obtaining a representation of the gaze data in a desired way.
  • the mapped 3D gaze endpoints over time are visualized in the scene image by visualizing the 3D gaze endpoints together with the corresponding frequency of views or accumulated viewing time, possibly distinguished according to different subjects.
  • said 3D Structure Detector repeatedly determines said 3D structure to enable a real-time gaze point detection using said eye tracker and said head tracker even if said 3D scene is not static, or said 3D scene Structure Detector initially determines said 3D structure and an object tracker tracks the movement of one or more objects in the scene to thereby enable a gaze point determination over time using the tracked objects and the tracked gaze direction over time.
  • said 3D Structure detection unit comprises one or more scene cameras and a computation unit for calculating said 3D structure based on said one or more cameras' images.
  • the 3D-structure detection unit can be implemented without specific hardware except a scene camera and a computation unit.
  • the scene camera(s) may be the same scene camera as is used for taking the scene image into which later the gaze endpoint is to be mapped
  • said computation unit uses a visual SLAM (visual Simultaneous Localization and Mapping) algorithm for calculating said 3D structure and/or the position of the scene camera.
  • visual SLAM visual Simultaneous Localization and Mapping
  • the system comprises: a display unit for displaying gaze data from one or more person with a visualization of statistic data on the reference model, wherein said visualization comprises:
  • the images of the one or more scene cameras are combined to one or more bigger images such as a panorama or a multiperspective image to be used as scene image or images, and/or and/or wherein said 3D structure representation unit uses the 3D structure and position of objects of the scene in the reference coordinate system to provide a 3D structure representation of the scene which has been determined in advance.
  • Using a 3D structure representation unit instead of a structure determination unit makes it possible to use 3D data which has been determined in advance.
  • a determination of a gaze endpoint and in one embodiment also a mapping of the gaze endopint not just for planes but for general objects in 3D-space. Moreover, according to one embodiment it can be determine which object in 3D-space a subject is gazing at.
  • a 3D-structure detector an object tracker for tracking the head of the subject and its orientation (a "head tracker") and an eye tracker.
  • head tracker By tracking the head movement using the head tracker and the gaze direction of the eye of the subject using the eye tracker there can be obtained the gaze direction of the subject in the 3D-space.
  • This gaze direction can then be projected or intersected with the 3D-model of the "world” which is obtained from the 3D-structure detector and viewed by the subject.
  • the point in the 3D-model to which the gaze of the subject is directed and where it is "hitting an object” of the 3D structure can be determined.
  • the "gaze endpoint” and thereby also the object at which the subject gazes at can be determined.
  • the gaze endpoint is determined based on the vergence of the eyes.
  • the eyetracker detects the gaze direction of the two eyes of the subject. When the subject looks at a certain object, then the gaze directions of the two eyes are not parallel but they are directed to the same object which means that they intersect at the point of regard the subject is looking at. This means that if the gaze directions of the two eyes are obtained by the eyetracker, the calculation of the intersection of the thus obtained gaze directions in 3D-space actually provides the point of regard in 3D space.
  • the two gaze directions which are determined for the two eyes of the subject do in fact not intersect at a certain point in space.
  • the reason may be that there is indeed no intersection, which means that the two gaze directions indeed do not converge and intersect at the same point in space, or the lack of an intersection point may be caused by a measurement error.
  • there may still be determined a gaze endpoint based on an intersection, e.g. by choosing the point which lies halfway on the distance vector between the two gaze directions, in other words the point in 3D space which lies closest to the two gaze directions.
  • This representation can be e.g. a full 3D structure representation of the objects which are according to one embodiment obtained by a structure generation unit.
  • the 3D structure representation of the objects define the structure of the objects (e.g. by their boundaries). If the gaze endpoint determination is exact and without error, then it typically will lie on the surface of an object of the 3D structure, and this is then the point which is determined as the point the subject is gazing at. Once the gaze endpoint has been determined, from the 3D structure representation there also follows the object the gaze endpoint is lying on, and thereby the object the user is gazing at.
  • the gaze endpoint does not lie on an object. This may be due to different reasons, one being e.g. that the gaze endpoint determined by vergence is not fully correct and exact, and then the thus determined gaze endpoint may lie somewhere in empty space where no object is located. According to one embodiment, however, even in such a situation there may be determined the object being gazed at, e.g. by determining the object which is closest to the gaze endpoint. This object may then be chosen as the one for which it has been determined that the subject is gazing at it.
  • Another approach for determining the object gazed at by the subject is checking if both gaze vectors intersect with the volume of the object.
  • the object with which both gaze vectors intersect is determined to be the object at which the user is gazing.
  • the gaze directions of the two eyes may be used to determine a "combined" gaze direction. This can e.g. be done by first calculating the gaze endpoint based on the vergence as the intersection of the gaze direction of the two eyes. The resulting gaze endpoint then can be used to determine a gaze direction which is based on the gaze direction of the two eyes, in other words a "combined gaze direction". This can be done by choosing as gaze direction a vector which originates e.g. between the eyes of the subject and passes through gaze endpoint which has been determined based on the intersection. The resulting combined gaze direction can then be used for calculating its intersection with an object of the 3D structure to determine the object being gazed at.
  • the eye tracking unit which is adapted to determine the gaze direction of the one or more eyes of the subject is adapted to determine a probability distribution of the gaze direction of the eye or the eyes.
  • This probability distribution may indicate for a determined gaze direction a likelihood of being correct. It can e.g. be obtained based on the (known or estimated) accuracy or "error distribution" of the eye tracker. This accuracy gives for a measurement value (i.e. the gaze direction) the probability that it is correct and - in form of a probability distribution - indicates for different values the likelihood that they are the correct measurement value. Using such a probability distribution one can - for the points in 3D space - indicate the probability that they are lying on the measured gaze direction.
  • This probability distribution is used to determine for a plurality of objects their corresponding probability of being gazed at.
  • the probability distribution of the measured gaze direction corresponds to a probability distribution of different gaze endpoints.
  • the probability distribution thereby may e.g. reflect the error distribution of the measured gaze direction.
  • the error distribution indicates the different likelihoods of different gaze directions being correct due to some measurement error (as indicated by the error distribution or "probability distribution"). Because for these different gaze directions there are resulting different gaze endpoints one can, based on the different gaze endpoints and their corresponding probabilities, obtain the respective probabilities of the corresponding objects being gazed at. This can e.g.
  • the "calculating unit for determining the object being gazed at” therefore actually determines the probability of an object being gazed as an implementation of the "determination of the object being gazed at”, in other words this is a specific embodiment of a calculating unit for determining the object being gazed at.
  • the probability distribution of the gaze direction can be used also for the gaze directions determined for the two eyes of the subject.
  • each of the two gaze directions has its own probability distribution which reflects the likelihood of a certain gaze direction being correct.
  • This probability distribution according to one embodiment is used to determine the probability of a certain object being gazed at; it follows directly from the probability distribution of the gaze endpoints.
  • the probability distribution of the gaze direction reflects the "accuracy" or "error” of the measurement of the gaze direction. It may be determined by measuring the error distribution or it may just be estimated. According to a further embodiment not only the gaze direction is determined with a certain error being reflected by a probability distribution but also the position of the objects in 3D space. For each object in 3D space there is according to one embodiment an uncertainty of its accuracy which is reflected by a probability distribution with respect to the location of the object. This probability distribution can then be combined with the probability distribution of the gaze direction(s) or the probability distribution of the gaze endpoints to obtain a combined probability for a certain object being gazed at which reflects both uncertainties.
  • each object need not to be represented by a full 3D representation of their shape, location and orientation.
  • each object may just be represented by one representative point in space which represents the location of the object in the 3D space.
  • This representative point may e.g. be the center of gravity of the 3D object.
  • it may be any point, e.g. a user defined or user selected point, which represents the location of the object in 3D space may be chosen as representative point in 3D space which represents the location of the object.
  • the location of multiple objects may be represented in 3D space.
  • the object may also not just be represented by a single point, it may be represented by some representative 3D representation which has some extension in two or 3 dimensions, e.g. by a plane area, or by a 3D shape like a sphere which has a representative point as a center.
  • some representative 3D representation which has some extension in two or 3 dimensions, e.g. by a plane area, or by a 3D shape like a sphere which has a representative point as a center.
  • Fig. 1A shows an example of a 3D real world scene. It includes a table and a lamp hanging from the ceiling as real world objects. The 3D representation of these objects is illustrated in Fig. 1B .
  • the lamp is represented by a sphere having a center C in 3D space and a radius R.
  • the table is represented by a rectangle with its corners X1, X2, X3 and X4.
  • the coordinates of X1 to X4 and C may be determined by some measurement to determine the 3D coordinates.
  • the radius R may be chosen such that it somehow resembles the shape of the "real lamp".
  • Fig. 1B This then results in a configuration as shown in Fig. 1B with two objects whose 3D location is represented by some representation in 3D space. Also shown is the head of the subject S.
  • the position and orientation of the head in 3D space may be determined by some object tracker (not shown), the gaze directions are obtained by some eyetracker, e.g. a head-mounted eyetracker (not shown).
  • some eyetracker e.g. a head-mounted eyetracker (not shown).
  • the gaze directions L1 and L2 in 3D space This will later be explained in even more detail.
  • the gaze direction intersection point G is determined as the point of regard based on the vergence. As can be seen from Fig. 1B it does not lie on one of the object representations, neither on the lamp nor on the table. Then there is determined the distance from the gaze point G to the table and the lamp. It can be seen that the distance to the table D1 is closer than to the lamp, and therefore the system then can conclude that the subject gazes at the table.
  • the system can determine the object a user is gazing at in 3D space.
  • the 3D representation of the objects uses a more accurate representation with higher granularity, e.g. a mesh representing the surface of the objects in 3D.
  • the system then may operate in the same manner. If the gaze point is determined more accurately and lies on or near the surface of the 3D object representation, then the system may not only determine the object the subject is gazing at but even the location on the object the user is gazing at.
  • the objects are represented by a 3D structure representation, and the object the subject is gazing at is determined based on the intersection of the gaze direction with the 3D object representation rather than based on vergence.
  • a system for mapping a gaze onto a 3D-object operates as follows.
  • a detector to measure 3D Scene Structure is used to determine the surface structure, position and orientation of all or all relevant (e.g. selected ones or objects larger than a minimum size) objects in the scene resulting in a reference model (a 3D structure or "model of the 3D structure" of the "real world”).
  • This reference model is a representation of the "world” which the user gazes at. It consists of a representation of the objects of the "world”, e.g. by a mesh.
  • the reference coordinate system is time invariant and static, in contrary e.g. to the coordinate system of a head mounted eye tracker which moves together with the head of the subject.
  • the eye's position (the same applies to multiple eyes) can be measured at any time in relation to the 3D Detector and in extension to the detected scene objects by using a Head Tracker that relates the eye's position to the 3D detector position and/or the head tracker's position (and thereby gives also its position in the reference coordinate system).
  • a Head Tracker that relates the eye's position to the 3D detector position and/or the head tracker's position (and thereby gives also its position in the reference coordinate system).
  • the head tracker coordinate system is time invariant as is the reference coordinate system of the 3D structure detection unit. In one example both coordinate systems are identical, in another example there may be a time invariant transformation which transforms the head tracker coordinate system to the reference coordinate system of the 3D structure detection unit or vice versa.
  • the gaze intersection with surfaces of objects of the 3D structure can be calculated.
  • the head-mounted eye tracker outputs the gaze direction in the coordinate system of the head/eye tracker. Since the head position and its orientation is known from the head tracker, the location and orientation of the eye tracker also is known due to the known setup of the eye tracker being head mounted. Using this information from the head tracker the gaze direction in the reference coordinate system (the system in which the 3D structure is represented) can be derived based on the gaze direction determined by the eye tracker in the eye tracker coordinate system by a simple transformation of the eye tracker coordinate system to the reference coordinate system. The transformation follows directly from the measured location and orientation of the head measured by the head tracker.
  • This gaze direction can then be intersected with the 3D structure representation of the scene to detect the 3D gaze endpoint on an object of the 3D structure.
  • a measurement device that measures the gaze endpoint of a person's (or a subject's) eye on 3D objects in the scene as well as parameters of the objects themselves.
  • the approach extends over the previous approach of determining the gaze point on a real scene plane by now detecting a 3D gaze endpoint on a 3D structure detected by the 3D-structure detector. Because the previous approach using a scene plane operates only in a 2D space it does not cover points with parallax induced by object points off the plane, of which there are usually plenty in real scenes. Therefore the present approach also overcomes such parallax problems.
  • the gaze endpoint on a 3D object can also be mapped to any image of the scene taken from any arbitrary location by a camera.
  • the camera's parameters and its position relative to the scene are needed. They may be known by definition of the setup/calibration, or both can also be calculated out of the image itself given the scene structure, or they may be otherwise measured.
  • the scene image is not taken by a scene camera but instead is generated based on the 3D structure representation, e.g. by projecting the structure into the image plane of the (arbitrary) scene image. Then in this arbitrary scene image the object of the 3D structure which has been determined as the object being gazed may be highlighted, or the gaze endpoint of the subject may be visualized by projecting it from the 3D structure into the scene image.
  • a user can name objects or even more detailed object parts of the 3D structure by hand.
  • objects may be "tagged” with a name so that a "hit" of the gaze on such a named object then results in the return of the corresponding object name.
  • this has to be done only once and the gaze on any object can be determined for all participants and for all times any of the participants observed the scene. This is because the true 3D model of the object can cope with all possible views which may be taken by a user.
  • the system in one embodiment may assign default names.
  • the reference model can be created offline. This is schematically illustrated in Fig. 2 .
  • the 3D-model /reference model is created "offline" using the 3D Structure Detector before the actual gaze measurement (this is illustrated as step a) in the upper part of Fig. 2 .
  • the 3D Structure Detector is not needed afterwards - the ET (eye tracker) and HT (head tracker) combination is then sufficient to determine the 3D gaze endpoint on the 3D structure which was determined in step a). This is illustrated in the upper part of step b) illustrated in Fig. 2 which shows the determination of the gaze endpoint on the 3D structure.
  • mapping of the gaze endpoint onto the scene image taken by a scene camera can be performed.
  • any 3D projection method which maps the 3D structure to a 2D scene image using the position and parameters of the camera can be used.
  • the location where the gaze hits the 3D structure can be mapped onto the corresponding location at a scene image taken by a scene camera.
  • This mapping process is schematically illustrated in the lower part of step b) in Fig. 2 which shows the mapping process (e.g. performed by using a 3D projection) of the 3D structure to a scene image.
  • the 3D Structure Detector works in parallel to the ET and HT. This is schematically illustrated in Fig. 3 where the 3D structure is determined parallel to the determination of the gaze by the ET, the head position of the HT, and the gaze endpoint mapping to a scene image.
  • the dynamic change of a scene can be taken into account by another mechanism.
  • the 3D structure is determined only once, initially.
  • the position and orientation of the relevant objects of the scene in the 3D space may be detected and tracked over time by one or more object trackers.
  • the gaze direction also is tracked over time. Based on the thus obtained tracking data there can then be performed an offline processing which determines over time the intersection between the gaze direction and the moving objects and thereby determines the dynamic gaze endpoint.
  • the components of this embodiment are gaze tracker, head tracker and 3D structure Detector.
  • the gaze tracking can be realized by any of the conventional eye trackers. If a calibration is needed, the eye tracker is calibrated to a known plane in space so the gaze direction can be calculated from the gaze point on the plane.
  • head trackers e.g. the following devices may be used:
  • the scene camera in combination with the detected objects to calculate the scene camera's position and orientation.
  • the camera may be the same scene camera as is used for taking the scene image into which later the gaze endpoint is to be mapped.
  • a visual SLAM approach For the purpose of determining the camera position there may be used a visual SLAM approach.
  • a description of the visual SLAM approach can e.g. be found in Andrew J. Davison, "Real-Time Simultaneous Localisation and Mapping with a Single Camera", ICCV2003 , or in Richard A. Newcombe and Andrew J. Davison, "Live Dense Reconstruction with a Single Moving Camera", CVPR2010 .
  • the camera position may just be measured, e.g. by internal sensors of the camera (e.g. a GPS sensor), or it may be determined in some other way (e.g. by an Inertial Measurement Unit or an object tracker).
  • internal sensors of the camera e.g. a GPS sensor
  • it may be determined in some other way (e.g. by an Inertial Measurement Unit or an object tracker).
  • the ET position relative to the scene camera is known through the setup (both mounted on the same frame).
  • Such measurement devices are e.g.
  • the plans for buildings are known in advance, e.g. from the construction plan, or the plans may have been derived by some "manual measurement”.
  • the 3D structure detection unit may then consist in just a device for "obtaining” or “reading” the stored 3D structure data which has been measured in advance, without performing an actual structure determination.
  • a 3D structure detection unit there may therefore be used a 3D structure representation unit which uses the 3D structure and position of objects of the scene in the reference coordinate system to provide a 3D structure representation of the scene.
  • the measurement of the 3D structure may have been carried out in advance, and the structure representation unit then just uses the previously measured data to provide the 3D structure representation.
  • a camera e.g. the scene camera
  • a visual SLAM approach e.g. the approach for static scenes to capture a video of the relevant scene part and calculate the scene structure by using a visual SLAM approach.
  • the approach allows also calculating the position of a camera taking an image of the scene from the image itself.
  • the structure can be measured online, which means that the 3D structure is repeatedly determined to take into account its dynamic changes. Otherwise a combination of offline (or initial) 3D structure detection and tracking of the object(s) of interest (e.g. with the help of an object tracker) can be used.
  • the structure can be measure once in advance.
  • the system comprises an eye tracker that provides the gaze direction of a person relative to the coordinate frame of the head.
  • the gaze direction can also be defined indirectly as long it can be transformed to a head relative coordinate system.
  • the system comprises a Head Tracker that detects the head or the eye tracker's coordinate system's location and orientation relative to a scene coordinate system. This can e.g. be done using sensors. In some cases these sensors detect their own position relative to the scene, then the sensor would need to be head mounted. However, any head tracking device may be used.
  • the system comprises a 3D Structure Detector that measures the three dimensional surface structure of objects.
  • the structure is made up out of the location, orientation and neighborhood of surface parts (points, patches, planes, or similar features used for describing 3D structure).
  • the detector may also measure appearance of the objects.
  • the system also comprises a scene camera (possibly combined with a position detecting device so its position and orientation is known) that makes reference images of the scene.
  • a scene camera possibly combined with a position detecting device so its position and orientation is known
  • the gaze point on a 3D structure there can be determined the gaze point on a 3D structure.
  • the scene image and the scene camera's position there can be performed a mapping of the 3D gaze point onto the scene image.
  • Such a mapping can be performed onto any scene image given that the camera position of the camera which takes the scene image is known, e.g. by using 3D projection of the 3D-gaze point onto the scene image.
  • the location of the gaze point in an arbitrary scene image can be performed in a slightly different way. Assuming that the gaze point at a first scene image has already been determined, then for a second scene image taken form a different position the gaze point mapping procedure as described in European patent application no. 11158922.2 can be used.
  • the 3D Structure Detector, Head Tracker, and position detecting device can all be implemented by a camera combined with a suitable method to extract the necessary information out of the images.
  • the eye tracker only needs to be combined with a scene camera and a device (such as a computer which is suitably programmed) that carries out the extraction methods to extract the data such as the 3D structure, the camera position and the head position.
  • a remote eye tracker may be used instead of a head-mounted eye tracker. If this remote eye tracker is located at a fixed position and has a fixed coordinate system, its coordinate system may be used as reference coordinate system or it at least has a known spatial relationship with the reference coordinate system of the 3D structure detector. If the remote eye tracker is capable of directly obtaining the gaze direction in its own time invariant coordinate system, then no further "separate" head tracker is needed, the eye tracker then - by the determination of the eye position and orientation which is performed also by such an eye tracker - simultaneously is also an implementation of a head tracking unit.
  • the scene camera can move relative to the eyetracker. Its position may be determined by an object tracker and then the gaze point may be projected onto the scene image as described before regardless of its position.

Claims (15)

  1. Un système comprenant :
    une unité de poursuite des yeux apte à déterminer les directions du regard (L1, L2) de deux yeux d'un sujet ;
    une unité de poursuite de sujet apte à déterminer une position comprenant l'emplacement et l'orientation de la tête du sujet et/ou de l'unité de poursuite des yeux dans un système de coordonnées de référence ;
    une unité de représentation de structure de scène tridimensionnelle qui représente une pluralité d'objets d'une scène dans le monde réel par le biais de leurs structures et/ou positions tridimensionnelles par le biais de coordonnées dans le système de coordonnées de référence pour produire ainsi une représentation de structure tridimensionnelle de la scène ;
    une unité de calcul pour :
    déterminer un point de fixation du regard (G) dans le système de coordonnées de référence en fonction de l'intersection des directions du regard des deux yeux du sujet et de la position ;
    déterminer une pluralité de distances respectives (D1, D2) entre le point de fixation du regard et la pluralité d'objets ; et
    déterminer quel objet de la pluralité d'objets regarde le sujet en fonction des distances respectives entre le point de fixation du regard et la pluralité d'objets.
  2. Le système de la revendication 1, dans lequel l'objet de la pluralité d'objets que regarde le sujet est déterminé en choisissant l'objet qui présente la plus faible distance respective entre le point de fixation du regard et l'objet.
  3. Le système de la revendication 1 ou 2, dans lequel
    l'unité de poursuite des yeux est apte à déterminer une distribution probabiliste du point de fixation du regard, et dans lequel
    l'unité de calcul est apte à déterminer la probabilité respective d'un ou plusieurs de la pluralité d'objets qui sont l'objet de la pluralité d'objets qui est regardé en fonction de la distribution probabiliste du point de fixation du regard.
  4. Le système de l'une des revendications 1 à 3 comprenant en outre :
    une caméra de scène apte à acquérir une ou plusieurs images de la scène depuis un point de vue arbitraire ;
    un module apte à cartographier le point de fixation du regard dans le système de coordonnées de référence sur le plan image de l'image de scène de la scène, dans lequel
    la position de la caméra de scène est connue ou déterminée par un quelconque mécanisme de détermination de position ou de poursuite d'objet et la cartographie est opérée en effectuant une projection du point de fixation du regard sur l'image de la scène.
  5. Le système de l'une des revendications 1 à 3 comprenant en outre :
    un module pour générer une image de scène telle que vue depuis un point de vue arbitraire en fonction de la représentation de structure tridimensionnelle ;
    un module pour cartographier un point de fixation du regard dans le système de coordonnées de référence sur le plan image de l'image de scène, la cartographie étant effectuée en effectuant une projection du point de fixation du regard dans le système de coordonnées de référence sur le plan image de l'image de scène.
  6. Le système de la revendication 4, dans lequel l'appareil de poursuite des yeux est un appareil de poursuite des yeux monté sur la tête ; et/ou
    la caméra de scène est une caméra de scène montée sur la tête.
  7. Le système de l'une des revendications 1 à 6, dans lequel
    l'unité de représentation de structure de scène tridimensionnelle comprend une unité de détection de structure tridimensionnelle qui est apte à déterminer la position et la structure tridimensionnelle d'objet de la scène ou leur structure de surface géométrique dans le système de coordonnées de référence pour obtenir une représentation de structure tridimensionnelle de la scène, dans lequel
    ladite unité de détection de structure tridimensionnelle comprend l'un des suivants :
    un scanner laser éventuellement combiné avec une caméra ;
    un scanner optique ensemble avec une source lumineuse émettant une lumière structurée ;
    un système de caméra stéréoscopique,
    un détecteur à ultrasons ; et
    toute mise en œuvre mécanique utilisable pour détecter un objet tridimensionnel.
  8. Le système de l'une des revendications 1 à 7, dans lequel :
    des points de fixation du regard tridimensionnels sont cartographiés sur une ou plusieurs images de scène prises par une pluralité de caméras de scène différentes et/ou sur des images de scène prises depuis des points de vue différents ;
    des points de fixation du regard tridimensionnels sont cartographiés pour une pluralité de sujets différents sur la même image de scène ; et/ou des points de fixation du regard tridimensionnels sont cartographiés ou agrégés dans le temps sur la même image de scène.
  9. Le système selon la revendication 8, dans lequel
    les points de fixation du regard tridimensionnels cartographiés dans le temps sont visualisés dans l'image de scène par visualisation des points de fixation du regard tridimensionnels ensemble avec la fréquence correspondante des vues ou du temps de visualisation cumulé, éventuellement distingués entre des sujets différents.
  10. Le système selon la revendication 9, dans lequel ladite visualisation utilise une ou plusieurs parmi :
    une carte thermique ;
    une carte de focalisation ;
    un centre de gravité du regard ; et/ou
    un contour automatique du temps de visualisation.
  11. Le système de la revendication 7, dans lequel
    l'unité de détection de structure de scène tridimensionnelle détermine de façon répétée la structure tridimensionnelle pour permettre une détection du point de fixation du regard en temps réel par utilisation de l'appareil de poursuite des yeux et d'un appareil de poursuite de la tête même si ladite scène tridimensionnelle n'est pas statique, ou
    l'unité de détection de structure de scène tridimensionnelle détermine une fois la structure tridimensionnelle et un appareil de poursuite d'objet opère la poursuite du déplacement d'un ou plusieurs objets dans la scène pour permettre ainsi une détermination du point de fixation du regard dans le temps en utilisant les objets poursuivis et la direction du regard poursuivi dans le temps.
  12. Le système de la revendication 7, dans lequel l'unité de détection de structure tridimensionnelle comprend une ou plusieurs caméras de scène et une unité de calcul pour le calcul de la structure tridimensionnelle en fonction des images desdites une ou plusieurs caméras, et/ou dans lequel ladite unité de calcul utilise un algorithme visuel SLAM, localisation et cartographie visuelles simultanées, pour calculer la structure tridimensionnelle et/ou la position de la caméra de scène.
  13. Le système selon l'une des revendications 1 à 12, dans lequel les images des une ou plusieurs caméras de scène sont combinées en une ou plusieurs plus grandes images de manière à pouvoir utiliser un panorama ou une image en perspectives multiples en tant qu'image ou images de scène, et/ou dans lequel ladite unité de représentation de structure tridimensionnelle utilise la structure tridimensionnelle et la position d'objet de la scène dans le système de coordonnées de référence pour produire une représentation de structure tridimensionnelle de la scène qui a été déterminée à l'avance.
  14. Le système selon l'une des revendications 1 à 13, dans lequel le point de fixation du regard s'étend dans un espace vide de la représentation de structure tridimensionnelle de la scène.
  15. Un procédé comprenant :
    la détermination des directions des regards (L1, L2) de deux yeux d'un sujet par un appareil de poursuite des yeux ;
    la détermination d'une position comprenant l'emplacement et l'orientation d'une tête du sujet et/ou de l'appareil de poursuite des yeux dans un système de coordonnées de référence ;
    la représentation d'une pluralité d'objets d'une scène dans le monde réel par le biais de leur position et/ou structure tridimensionnelles par l'intermédiaire de coordonnées dans le système de coordonnées de référence pour produire ainsi une représentation de structure tridimensionnelle de la scène ;
    la détermination d'un point de fixation du regard (G) dans le système de coordonnées de référence en fonction de l'intersection des directions du regard des deux yeux du sujet et de la position ;
    la détermination d'une pluralité de distances respectives (D1, D2) entre le point de fixation du regard et la pluralité d'objets ; et
    la détermination de celui des objets de la pluralité d'objets que regarde le sujet en fonction des distances respectives entre le point de fixation du regard et la pluralité d'objets.
EP12184725.5A 2012-09-17 2012-09-17 Procédé et appareil permettant de déterminer un point de regard fixe sur un objet tridimensionnel Active EP2709060B1 (fr)

Priority Applications (10)

Application Number Priority Date Filing Date Title
EP12184725.5A EP2709060B1 (fr) 2012-09-17 2012-09-17 Procédé et appareil permettant de déterminer un point de regard fixe sur un objet tridimensionnel
CN201380048140.XA CN104685541B (zh) 2012-09-17 2013-09-17 用于确定三维对象上注视点的方法和装置
JP2015531598A JP6808320B2 (ja) 2012-09-17 2013-09-17 三次元物体上の注視点を決定するシステム
PCT/EP2013/069236 WO2014041188A1 (fr) 2012-09-17 2013-09-17 Procédé et appareil permettant de déterminer une cible de regard sur un objet tridimensionnel
US14/428,608 US10223808B2 (en) 2012-09-17 2013-09-17 Method and an apparatus for determining a gaze point on a three-dimensional object
IN1984DEN2015 IN2015DN01984A (fr) 2012-09-17 2013-09-17
US16/290,934 US10699439B2 (en) 2012-09-17 2019-03-03 Method and an apparatus for determining a gaze point on a three-dimensional object
JP2019071195A JP6690041B2 (ja) 2012-09-17 2019-04-03 三次元物体上の注視点決定方法及び装置
US16/878,932 US11676302B2 (en) 2012-09-17 2020-05-20 Method and an apparatus for determining a gaze point on a three-dimensional object
US18/111,099 US11948332B2 (en) 2012-09-17 2023-02-17 Method and an apparatus for determining a gaze point on a three-dimensional object

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
EP12184725.5A EP2709060B1 (fr) 2012-09-17 2012-09-17 Procédé et appareil permettant de déterminer un point de regard fixe sur un objet tridimensionnel

Publications (2)

Publication Number Publication Date
EP2709060A1 EP2709060A1 (fr) 2014-03-19
EP2709060B1 true EP2709060B1 (fr) 2020-02-26

Family

ID=47010238

Family Applications (1)

Application Number Title Priority Date Filing Date
EP12184725.5A Active EP2709060B1 (fr) 2012-09-17 2012-09-17 Procédé et appareil permettant de déterminer un point de regard fixe sur un objet tridimensionnel

Country Status (6)

Country Link
US (4) US10223808B2 (fr)
EP (1) EP2709060B1 (fr)
JP (2) JP6808320B2 (fr)
CN (1) CN104685541B (fr)
IN (1) IN2015DN01984A (fr)
WO (1) WO2014041188A1 (fr)

Families Citing this family (47)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9811731B2 (en) * 2013-10-04 2017-11-07 Qualcomm Incorporated Dynamic extension of map data for object detection and tracking
JP6268303B2 (ja) * 2014-02-04 2018-01-24 フラウンホーファー−ゲゼルシャフト・ツール・フェルデルング・デル・アンゲヴァンテン・フォルシュング・アインゲトラーゲネル・フェライン ２ｄ画像分析装置
JP2015219892A (ja) * 2014-05-21 2015-12-07 大日本印刷株式会社 視線分析システムおよび視線分析装置
CN106796443A (zh) * 2014-08-07 2017-05-31 Fove股份有限公司 三维上的凝视点的位置确定方法
US10228766B2 (en) * 2014-09-12 2019-03-12 Microsoft Technology Licensing, Llc Enhanced Display Rotation
JP6547268B2 (ja) * 2014-10-02 2019-07-24 富士通株式会社 視線位置検出装置、視線位置検出方法及び視線位置検出プログラム
JP6663441B2 (ja) * 2015-03-01 2020-03-11 ノバサイト リミテッド 眼球運動を測定するためのシステム
JP6839656B2 (ja) 2015-03-23 2021-03-10 コントローラッド システムズ、インコーポレイテッドＣｏｎｔｒｏｌｒａｄ Ｓｙｓｔｅｍｓ，Ｉｎｃ． 視標追跡システム
WO2016179825A1 (fr) * 2015-05-14 2016-11-17 中国科学院深圳先进技术研究院 Procédé de navigation basé sur une scène tridimensionnelle
GB2539009A (en) * 2015-06-03 2016-12-07 Tobii Ab Gaze detection method and apparatus
US9829976B2 (en) * 2015-08-07 2017-11-28 Tobii Ab Gaze direction mapping
US10444972B2 (en) 2015-11-28 2019-10-15 International Business Machines Corporation Assisting a user with efficient navigation between a selection of entries with elements of interest to the user within a stream of entries
JP2017129898A (ja) 2016-01-18 2017-07-27 ソニー株式会社 情報処理装置、情報処理方法、およびプログラム
TWI589150B (zh) * 2016-03-04 2017-06-21 液態三維系統有限公司 ３ｄ自動對焦顯示方法及其系統
WO2017153355A1 (fr) * 2016-03-07 2017-09-14 SensoMotoric Instruments Gesellschaft für innovative Sensorik mbH Procédé et dispositif d'exécution de rendu d'un regard
US10063560B2 (en) * 2016-04-29 2018-08-28 Microsoft Technology Licensing, Llc Gaze-based authentication
WO2017208227A1 (fr) 2016-05-29 2017-12-07 Nova-Sight Ltd. Système et procédé d'affichage
KR20190006553A (ko) * 2016-06-16 2019-01-18 센소모토릭 인스트루멘츠 게젤샤프트 퓌어 이노바티브 센소릭 엠베하 사용자 거동에 관한 눈 추적 기반 정보를 제공하기 위한 방법 및 시스템, 클라이언트 디바이스, 서버 및 컴퓨터 프로그램 제품
JP2020509790A (ja) 2016-09-23 2020-04-02 ノバサイト リミテッド スクリーニング装置及び方法
WO2018076202A1 (fr) * 2016-10-26 2018-05-03 中国科学院深圳先进技术研究院 Dispositif d'affichage monté sur la tête pouvant effectuer un suivi de l'œil, et procédé de suivi de l'œil
CN108338798B (zh) * 2017-01-25 2020-11-06 北京数字新思科技有限公司 一种注意力测量方法和系统
CN106840167B (zh) * 2017-02-23 2019-12-20 周良辰 基于街景地图的目标物地理位置的二维量测算方法
CN107223082B (zh) 2017-04-21 2020-05-12 深圳前海达闼云端智能科技有限公司 一种机器人控制方法、机器人装置及机器人设备
CN108965687B (zh) * 2017-05-22 2021-01-29 阿里巴巴集团控股有限公司 拍摄方向识别方法、服务器及监控方法、系统及摄像设备
CN107369205B (zh) * 2017-07-04 2020-10-16 东南大学 一种移动终端城市二三维联动显示方法
CN107392853B (zh) * 2017-07-13 2020-05-26 河北中科恒运软件科技股份有限公司 双摄像头视频融合畸变校正与视点微调整方法及系统
US10853965B2 (en) * 2017-08-07 2020-12-01 Standard Cognition, Corp Directional impression analysis using deep learning
CN107504917B (zh) * 2017-08-17 2020-02-21 深圳市异方科技有限公司 一种三维尺寸测量方法及装置
KR102495359B1 (ko) 2017-10-27 2023-02-02 삼성전자주식회사 객체 트래킹 방법 및 장치
JP6916896B2 (ja) * 2017-11-16 2021-08-11 株式会社ソニー・インタラクティブエンタテインメント 情報処理装置および画像生成方法
WO2019161229A1 (fr) 2018-02-15 2019-08-22 DMAI, Inc. Système et procédé de reconstruction d'espace 3d non occupé
EP3752957A4 (fr) 2018-02-15 2021-11-17 DMAI, Inc. Système et procédé de compréhension de la parole par l'intermédiaire d'une reconnaissance vocale basée sur des signaux audio et visuel intégrés
US11017551B2 (en) * 2018-02-15 2021-05-25 DMAI, Inc. System and method for identifying a point of interest based on intersecting visual trajectories
US11468885B2 (en) 2018-02-15 2022-10-11 DMAI, Inc. System and method for conversational agent via adaptive caching of dialogue tree
CN114935974A (zh) 2018-03-30 2022-08-23 托比股份公司 用于确定注视关注目标的对物体映射的多线迹注视
TWI719343B (zh) * 2018-08-28 2021-02-21 財團法人工業技術研究院 資訊顯示方法及其顯示系統
WO2020068459A1 (fr) * 2018-09-28 2020-04-02 Apple Inc. Suivi de l'œil par fusion de capteurs
CN109491508B (zh) * 2018-11-27 2022-08-26 北京七鑫易维信息技术有限公司 一种确定注视对象的方法和装置
SE543121C2 (en) * 2019-02-04 2020-10-13 Tobii Ab Method and system for determining a current gaze direction
SE1950580A1 (en) * 2019-05-15 2020-10-13 Tobii Ab Method and system for dwell-less, hands-free interaction with a selectable object
CN112013844B (zh) * 2019-05-31 2022-02-11 北京小米智能科技有限公司 建立室内环境地图的方法及装置
US11181978B2 (en) 2019-06-17 2021-11-23 Hemy8 Sa System and method for gaze estimation
EP3839411B1 (fr) * 2019-12-17 2023-08-23 John Cockerill Defense SA Système intelligent pour le contrôle de fonctions dans une tourelle de véhicule de combat
CN112509007A (zh) * 2020-12-14 2021-03-16 科大讯飞股份有限公司 真实注视点定位方法以及头戴式视线跟踪系统
JP2023053631A (ja) * 2021-10-01 2023-04-13 株式会社日立製作所 注視位置分析システム及び注視位置分析方法
WO2023189218A1 (fr) * 2022-04-01 2023-10-05 ソニーグループ株式会社 Dispositif de traitement d'informations, procédé de traitement d'informations et support d'enregistrement
SE2250674A1 (en) 2022-06-03 2023-12-04 Tobii Ab Method of estimating a three-dimensional position of an object

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2010083853A1 (fr) * 2009-01-26 2010-07-29 Tobii Technology Ab Détection de point de regard aidé par des signaux optiques de référence

Family Cites Families (24)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1978418A2 (fr) * 1996-12-06 2008-10-08 Nippon Telegraph And Telephone Corporation Procédé et système de production d'hologrammes générés informatiquement permettant la production et l'affichage en temps réel de vidéo holographique
JPH10326071A (ja) * 1997-03-27 1998-12-08 Nippon Telegr & Teleph Corp <Ntt> 注視点高解像度化による計算機ホログラム表示方法並びに装置並びにこの方法を記録した記録媒体
KR20010079822A (ko) 1998-09-14 2001-08-22 엘리스, 티모씨, 더블유. 와이어 본딩 합금 복합재료
US7046924B2 (en) * 2002-11-25 2006-05-16 Eastman Kodak Company Method and computer program product for determining an area of importance in an image using eye monitoring information
JP2005071041A (ja) 2003-08-22 2005-03-17 Nissan Motor Co Ltd 運転者視対象検出装置及び運転者視対象検出システム
ZA200608191B (en) * 2004-04-01 2008-07-30 William C Torch Biosensors, communicators, and controllers monitoring eye movement and methods for using them
JP4875843B2 (ja) 2004-10-20 2012-02-15 オリンパス株式会社 情報端末装置
JP5044237B2 (ja) * 2006-03-27 2012-10-10 富士フイルム株式会社 画像記録装置、画像記録方法、および画像記録プログラム
JP4876687B2 (ja) 2006-04-19 2012-02-15 株式会社日立製作所 注目度計測装置及び注目度計測システム
JP2007319187A (ja) * 2006-05-30 2007-12-13 Toyota Motor Corp 動作補助装置及びその制御方法
US8781162B2 (en) * 2011-01-05 2014-07-15 Ailive Inc. Method and system for head tracking and pose estimation
KR100820639B1 (ko) * 2006-07-25 2008-04-10 한국과학기술연구원 시선 기반 3차원 인터랙션 시스템 및 방법 그리고 3차원시선 추적 시스템 및 방법
US8494229B2 (en) * 2008-02-14 2013-07-23 Nokia Corporation Device and method for determining gaze direction
CN201307266Y (zh) * 2008-06-25 2009-09-09 韩旭 双目视线跟踪装置
CN101419672B (zh) * 2008-12-03 2010-09-08 中国科学院计算技术研究所 一种同步采集人脸图像和注视视角的装置及方法
WO2010102037A2 (fr) * 2009-03-03 2010-09-10 The Ohio State University Système et procédé de mesure et d'entraînement du suivi du regard
CN101943982B (zh) 2009-07-10 2012-12-12 北京大学 基于被跟踪的眼睛运动的图像操作
JP5590487B2 (ja) * 2010-07-30 2014-09-17 公立大学法人広島市立大学 視線計測方法及び視線計測装置
US8408706B2 (en) * 2010-12-13 2013-04-02 Microsoft Corporation 3D gaze tracker
JP5924862B2 (ja) * 2010-12-15 2016-05-25 キヤノン株式会社 情報処理装置、情報処理方法及びプログラム
JP5522799B2 (ja) * 2011-02-18 2014-06-18 日本放送協会 視線位置推定システム及び視線位置推定プログラム
JP2013008365A (ja) * 2011-06-23 2013-01-10 Ailive Inc 運動感知型機器を用いる遠隔制御
US8885882B1 (en) * 2011-07-14 2014-11-11 The Research Foundation For The State University Of New York Real time eye tracking for human computer interaction
US9116926B2 (en) * 2012-12-20 2015-08-25 Google Inc. Sharing photos

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2010083853A1 (fr) * 2009-01-26 2010-07-29 Tobii Technology Ab Détection de point de regard aidé par des signaux optiques de référence

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
ANDREW T DUCHOWSKI ET AL: "Binocular eye tracking in virtual reality for inspection training", PROCEEDINGS EYE TRACKING RESEARCH & APPLICATIONS SYMPOSIUM 2000. (ETRA). PALM BEACH GARDENS, FL, NOV. 6 - 8, 2000, NEW YORK, NY : ACM, US, 8 November 2000 (2000-11-08), pages 89 - 96, XP058268054, ISBN: 978-1-58113-280-9, DOI: 10.1145/355017.355031 *
KENTARO TAKEMURA ET AL: "Estimating 3D point-of-regard and visualizing gaze trajectories under natural head movements", PROCEEDINGS OF THE 2010 SYMPOSIUM ON EYE-TRACKING RESEARCH & APPLICATIONS, ETRA '10, ACM PRESS, NEW YORK, NEW YORK, USA, 22 March 2010 (2010-03-22), pages 157 - 160, XP058123557, ISBN: 978-1-60558-994-7, DOI: 10.1145/1743666.1743705 *
SUSAN M. MUNN ET AL: "3D point-of-regard, position and head orientation from a portable monocular video-based eye tracker", EYE TRACKING RESEARCH & APPLICATIONS : PROCEEDINGS ; ETRA 2008 ; [EYE TRACKING RESEARCH AND APPLICATIONS SYMPOSIUM] ; SAVANNA, GEORGIA, USA, MARCH 26 - 28, 2008, 1 January 2008 (2008-01-01), New York, NY, pages 181, XP055352612, ISBN: 978-1-59593-982-1, DOI: 10.1145/1344471.1344517 *

Also Published As

Publication number Publication date
EP2709060A1 (fr) 2014-03-19
JP6690041B2 (ja) 2020-04-28
JP2015528359A (ja) 2015-09-28
US11676302B2 (en) 2023-06-13
US20230206494A1 (en) 2023-06-29
US20200334858A1 (en) 2020-10-22
CN104685541B (zh) 2019-03-05
IN2015DN01984A (fr) 2015-08-14
US10223808B2 (en) 2019-03-05
JP2019141620A (ja) 2019-08-29
WO2014041188A1 (fr) 2014-03-20
US11948332B2 (en) 2024-04-02
CN104685541A (zh) 2015-06-03
JP6808320B2 (ja) 2021-01-06
US20190272650A1 (en) 2019-09-05
US20150243036A1 (en) 2015-08-27
US10699439B2 (en) 2020-06-30

Similar Documents

Publication Publication Date Title
US11948332B2 (en) Method and an apparatus for determining a gaze point on a three-dimensional object
CN103501688B (zh) 注视点映射的方法和装置
CN106535806B (zh) 来自多端口视角的手术场景的定量三维成像
Mansouryar et al. 3D gaze estimation from 2D pupil positions on monocular head-mounted eye trackers
Paletta et al. 3D attention: measurement of visual saliency using eye tracking glasses
EP3769146B1 (fr) Détection de profondeur et détection de mouvement hybrides
Bouguet et al. 3D photography using shadows in dual-space geometry
US11276225B2 (en) Synthesizing an image from a virtual perspective using pixels from a physical imager array weighted based on depth error sensitivity
WO2018097831A1 (fr) Capture et restitution de champ lumineux pour des visiocasques
US20060152434A1 (en) Calibrating real and virtual views
WO2016095057A1 (fr) Suivi périphérique pour un dispositif monté sur la tête à réalité augmentée
WO2016029939A1 (fr) Procédé et système pour déterminer au moins une caractéristique d&#39;image dans au moins une image
CN105354825B (zh) 自动识别读写场景中读物位置的智能装置及其应用
JP2005185431A (ja) 視線検出方法および視線検出装置
JP6680207B2 (ja) 視線計測システム、視線計測方法、及びプログラム
CN105354822B (zh) 自动识别读写场景中读写元素位置的智能装置及应用
JP2015050693A (ja) カメラ設置シミュレータ及びそのコンピュータプログラム
JP6095032B1 (ja) 合成画像提示システム
Santner et al. Visual recovery of saliency maps from human attention in 3D environments
Desai et al. Combining skeletal poses for 3D human model generation using multiple Kinects
TWI792106B (zh) 資訊顯示方法及其處理裝置與顯示系統
CN116027910B (zh) 一种基于vr眼动追踪技术的眼位图生成方法及系统
Paletta et al. 3D recovery of human gaze in natural environments
TWI823740B (zh) 主動式互動導覽系統以及主動式互動導覽方法
Gaspar et al. Accurate infrared tracking system for immersive virtual environments

Legal Events

Date Code Title Description
PUAI Public reference made under article 153(3) epc to a published international application that has entered the european phase

Free format text: ORIGINAL CODE: 0009012

AK Designated contracting states

Kind code of ref document: A1

Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR

AX Request for extension of the european patent

Extension state: BA ME

17P Request for examination filed

Effective date: 20140919

RBV Designated contracting states (corrected)

Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: EXAMINATION IS IN PROGRESS

17Q First examination report despatched

Effective date: 20170317

RAP1 Party data changed (applicant data changed or rights of an application transferred)

Owner name: APPLE INC.

REG Reference to a national code

Ref country code: DE

Ref legal event code: R079

Ref document number: 602012068019

Country of ref document: DE

Free format text: PREVIOUS MAIN CLASS: G06T0007000000

Ipc: G06T0007730000

GRAP Despatch of communication of intention to grant a patent

Free format text: ORIGINAL CODE: EPIDOSNIGR1

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: GRANT OF PATENT IS INTENDED

RIC1 Information provided on ipc code assigned before grant

Ipc: G06T 7/73 20170101AFI20190819BHEP

Ipc: A61B 3/113 20060101ALI20190819BHEP

INTG Intention to grant announced

Effective date: 20190910

GRAS Grant fee paid

Free format text: ORIGINAL CODE: EPIDOSNIGR3

GRAA (expected) grant

Free format text: ORIGINAL CODE: 0009210

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE PATENT HAS BEEN GRANTED

AK Designated contracting states

Kind code of ref document: B1

Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR

REG Reference to a national code

Ref country code: GB

Ref legal event code: FG4D

REG Reference to a national code

Ref country code: CH

Ref legal event code: EP

REG Reference to a national code

Ref country code: AT

Ref legal event code: REF

Ref document number: 1238546

Country of ref document: AT

Kind code of ref document: T

Effective date: 20200315

REG Reference to a national code

Ref country code: IE

Ref legal event code: FG4D

REG Reference to a national code

Ref country code: DE

Ref legal event code: R096

Ref document number: 602012068019

Country of ref document: DE

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: RS

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20200226

Ref country code: FI

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20200226

Ref country code: NO

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20200526

REG Reference to a national code

Ref country code: NL

Ref legal event code: MP

Effective date: 20200226

REG Reference to a national code

Ref country code: LT

Ref legal event code: MG4D

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: HR

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20200226

Ref country code: GR

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20200527

Ref country code: LV

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20200226

Ref country code: SE

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20200226

Ref country code: IS

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20200626

Ref country code: BG

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20200526

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: NL

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20200226

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: SK

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20200226

Ref country code: CZ

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20200226

Ref country code: RO

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20200226

Ref country code: LT

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20200226

Ref country code: PT

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20200719

Ref country code: ES

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20200226

Ref country code: SM

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20200226

Ref country code: EE

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20200226

Ref country code: DK

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20200226

REG Reference to a national code

Ref country code: AT

Ref legal event code: MK05

Ref document number: 1238546

Country of ref document: AT

Kind code of ref document: T

Effective date: 20200226

REG Reference to a national code

Ref country code: DE

Ref legal event code: R097

Ref document number: 602012068019

Country of ref document: DE

PLBE No opposition filed within time limit

Free format text: ORIGINAL CODE: 0009261

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: NO OPPOSITION FILED WITHIN TIME LIMIT

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: IT

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20200226

Ref country code: AT

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20200226

26N No opposition filed

Effective date: 20201127

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: SI

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20200226

Ref country code: PL

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20200226

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: MC

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20200226

REG Reference to a national code

Ref country code: CH

Ref legal event code: PL

REG Reference to a national code

Ref country code: BE

Ref legal event code: MM

Effective date: 20200930

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: LU

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20200917

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: FR

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20200930

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: CH

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20200930

Ref country code: BE

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20200930

Ref country code: IE

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20200917

Ref country code: LI

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20200930

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: TR

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20200226

Ref country code: MT

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20200226

Ref country code: CY

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20200226

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: MK

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20200226

Ref country code: AL

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20200226

P01 Opt-out of the competence of the unified patent court (upc) registered

Effective date: 20230523

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: GB

Payment date: 20230727

Year of fee payment: 12

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: DE

Payment date: 20230726

Year of fee payment: 12